Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to support and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     e
    -0.15
     ra
    -0.15
    onds
    -0.15
    owie
    -0.14
    973
    -0.14
    RA
    -0.14
    olated
    -0.14
    isu
    -0.14
    orem
    -0.14
    alore
    -0.14
    POSITIVE LOGITS
    =DB
    0.16
    rez
    0.15
    izzie
    0.14
    zano
    0.14
    Falsy
    0.14
    deaux
    0.14
     Thrones
    0.14
    sled
    0.14
    Msp
    0.14
    Selective
    0.14
    Act Density 0.142%

    No Known Activations